Real-Time Disability Identification and Preferential Interaction Modification

1. A system for providing a webpage dynamically generated based on a disability of a user, comprising: a memory operable to store: a disability type database comprising information associated with one or more of a visual disability, a partial visual disability, a hearing disability, and hand disability, wherein information associated with a particular disability from among the one or more disabilities comprise a type of the particular disability; a disability guideline database comprising configurations to modify webpages for each disability; and website generation rules comprising rules to create webpages modified based on the configurations, wherein the rules to create the webpages for each disability comprise functions to generate HTML code of the webpages based on the configurations to modify webpages for each disability; a template repository comprising a plurality of templates of the webpage, wherein each template from among the plurality of templates of the webpage is associated with at least one different disability; a first processor, associated with a user device, operably coupled to the memory, configured to: detect a particular disability of a particular user facing the user device attempting to access a webpage on a web browser, wherein the particular disability of the particular user comprises at least one of a visual disability or a hearing disability; send a request to a server to modify the webpage based on the particular disability; and a second processor associated with the server, the second processor configured to: determine whether the particular disability exists in the disability type database; in response to a determination that the particular disability does not exist in the disability type database: retrieve configurations to modify the webpage for the particular disability from the disability guideline database; and dynamically modify the webpage for the particular disability using the retrieved configurations; send the dynamically modified webpage to the user device; the first processor is further configured to: receive the dynamically modified webpage from the second processor; and display the dynamically modified webpage on the web browser on the user device.

2. The system of claim 1 , wherein the second processor is further configured to: develop a disability recognition model, wherein: the disability recognition model comprises information to determine a disability of a user using an image of the user included in a training dataset; the training dataset comprises images of different users captured from cameras of user devices associated with the different users, and images of the different users captured from social media platforms associated with the different users; send the disability recognition model to the first processor to detect the disability of the user; and update the disability recognition model at configurable time intervals.

3. The system of claim 1 , wherein the second processor is further configured to: develop a disability recognition model, wherein: the disability recognition model comprises information to determine a disability of a user using an audio of the user included in a training dataset; the training dataset comprises audios of different users captured from microphones of user devices associated with the different users, and audios of the different users captured from social media platforms associated with the different users; send the disability recognition model to the first processor to detect the disability of the user; and update the disability recognition model at configurable time intervals.

4. The system of claim 1 , wherein the second processor is configured to choose a particular template of the webpage based on feedback received from different users with different disabilities accessing the webpage, wherein: the different templates of the webpage for different disabilities are stored in the template repository; and the different templates of the webpage for different disabilities comprise: a first template associated with a first hearing disability comprises a first text in a first font with a first font size in a first color and a first button with a first button size and a first text description added to a first image, a second text description added to a first audio, and a third text description added to a first video within the webpage; and a second template associated with a first visual disability comprises a first audio caption added to a text, a second audio caption added to an image, and a third audio caption added to a video within the webpage.

5. The system of claim 1 , wherein detecting the particular disability of the particular user facing the user device comprises: capturing an image of the particular user using a camera of the user device; extracting features of the image by a disability recognition model; comparing the features of the captured image of the particular user with features of images stored in a training dataset, wherein each image stored in the training dataset indicates a disability of a user; determining whether the features of the captured image match features of any of the images stored in the training dataset; and in response to determining that the features of the captured image match features of an image stored in the training dataset, determining that the particular user has the disability indicated in the image stored in the training dataset.

6. The system of claim 1 , wherein detecting a particular disability of the particular user facing the user device further comprises: capturing an audio sample of the particular user using a microphone of the user device; extracting features of the captured audio sample by a disability recognition model; comparing the features of the audio sample of the particular user with features of audio samples stored in a training dataset, wherein each audio sample stored in the training dataset indicates a disability of a user; determining whether the features of the captured audio sample match features of any of the audio samples stored in the training dataset; and in response to determining that the features of the captured audio sample match features of an audio sample stored in the training dataset, determining that the particular user has the disability indicated in the audio sample stored in the training dataset.

7. The system of claim 1 , wherein configurations for modifying the webpage for a partial visual disability comprise: an indication that specifies a particular range of font sizes to be used for text displayed on the webpage; an indication that specifies a particular range of contrasts to be used for items displayed on the webpage, wherein the items displayed on the webpage comprise text, images, videos, and buttons.

8. The system of claim 1 , wherein configurations for modifying the webpage for a visual disability comprise: an indication that specifies to add audio captions to text displayed on the webpage; an indication that specifies to add audio descriptions to images displayed on the webpage; and an indication that specifies to use voice of the particular user for navigating though the webpage, wherein the navigation through the webpage comprises moving up, moving down, accessing links, selecting buttons, and filling out forms.

9. The system of claim 1 , wherein configurations for modifying the webpage for a hearing disability comprise: an indication that specifies to add text descriptions to audios included in the webpage; an indication that specifies to add text descriptions to videos with audio included in the webpage; an indication that specifies to add a sign language display to audios included in the webpage; and an indication that specifies to add a sign language display to videos with audio included in the webpage.

10. The system of claim 1 , wherein the first processor is further configured to: store activities of the particular user on the webpage in the memory, wherein the activities of the particular user comprise navigating through the webpage and accessing links on the webpage; receive feedback from the particular user on the dynamically modified webpage; and use the feedback in choosing a template of the webpage for other users with a similar disability.

11. The system of claim 1 , wherein the second processor is further configured to: in response to a determination that the particular disability exists in the disability type database: choose a particular template of the webpage associated with the particular disability from the template repository; and send the dynamically modified webpage to the user device.

12. A method for providing a webpage dynamically generated based on a disability of a user, comprising: detecting, by a first processor, a particular disability of a particular user facing a user device attempting to access a webpage on a web browser, wherein the particular disability of the particular user comprises at least one of a visual disability or a hearing disability; sending, by the first processor, a request to a server to modify the webpage based on the particular disability; determining, by a second processor, whether the particular disability exists in a disability type database; in response to determining that the particular disability does not exist in the disability type database: retrieving configurations to modify the webpage for the particular disability from a disability guideline database; and dynamically modifying the webpage for the particular disability using the retrieved configurations; sending, by the second processor, the dynamically modified webpage to the user device; receiving, by the first processor, the dynamically modified webpage from the second processor; and displaying, by the first processor, the dynamically modified webpage on the web browser on the user device.

13. The method of claim 12 , wherein the method further comprises: developing a disability recognition model, wherein: the disability recognition model comprises information to determine a disability of a user using an image of the user included in a training dataset; and the training dataset comprises images of different users captured from cameras of user devices associated with the different users, and images of the different users captured from social media platforms associated with the different users; sending the disability recognition model to the first processor to detect the disability of the user; and updating the disability recognition model at configurable time intervals.

14. The method of claim 12 , wherein the method further comprises: developing a disability recognition model, wherein: the disability recognition model comprises information to determine a disability of a user using an audio of the user included in a training dataset; and the training dataset comprises audios of different users captured from microphones of user devices associated with the different users, and audios of the different users captured from social media platforms associated with the different users; sending the disability recognition model to the first processor to detect the disability of the user; and updating the disability recognition model at configurable time intervals.

15. The method of claim 12 , wherein the method further comprises: choosing a particular template of the webpage based on feedback received from different users with different disabilities accessing the webpage, wherein: the different templates of the webpage for different disabilities are stored in a template repository; and the different templates of the webpage for different disabilities comprises: a first template associated with a first hearing disability comprises a first text in a first font with a first font size in a first color and a first button with a first button size and a first text description added to a first image, a second text description added to a first audio, and a third text description added to a first video within the webpage; and a second template associated with a first visual disability comprises a first audio caption added to a text, a second audio caption added to an image, and a third audio caption added to a video within the webpage.

16. The method of claim 12 , wherein detecting the particular disability of the particular user facing the user device comprises: capturing an image of the particular user using a camera of the user device; extracting features of the image by a disability recognition model; comparing the features of the captured image of the particular user with features of images stored in a training dataset, wherein each image stored in the training dataset indicates a disability of a user; determining whether the features of the captured image match features of any of the images stored in the training dataset; and in response to determining that the features of the captured image match features of an image stored in the training dataset, determining that the particular user has the disability indicated in the image stored in the training dataset.

17. The method of claim 12 , wherein detecting a particular disability of the particular user facing the user device further comprises: capturing an audio sample of the particular user using a microphone of the user device; extracting features of the captured audio sample by a disability recognition model; comparing the features of the audio sample of the particular user with features of audio samples stored in a training dataset, wherein each audio sample stored in the training dataset indicates a disability of a user; determining whether the features of the captured audio sample match features of any of the audio samples stored in the training dataset; and in response to determining that the features of the captured audio sample match features of an audio sample stored in the training dataset, determining that the particular user has the disability indicated in the audio sample stored in the training dataset.

18. The method of claim 12 , wherein configurations for modifying the webpage for a partial visual disability comprise: an indication that specifies a particular range of font sizes to be used for text displayed on the webpage; an indication that specifies a particular range of contrasts to be used for items displayed on the webpage, wherein the items displayed on the webpage comprise text, images, videos, and buttons.

19. The method of claim 12 , wherein configurations for modifying the webpage for a visual disability comprise: an indication that specifies to add audio captions to text displayed on the webpage; an indication that specifies to add audio descriptions to images displayed on the webpage; and an indication that specifies to use voice of the particular user for navigating though the webpage, wherein the navigation through the webpage comprises moving up, moving down, accessing links, selecting buttons, and filling out forms.

20. The method of claim 12 , wherein configurations for modifying the webpage for a hearing disability comprise: an indication that specifies to add text descriptions to audios included in the webpage; an indication that specifies to add text descriptions to videos with audio included in the webpage; an indication that specifies to add a sign language display to audios included in the webpage; and an indication that specifies to add a sign language display to videos with audio included in the webpage.